Refactor PPO imitation loss behind env-owned adapter - #83
Merged
Conversation
PPO no longer hardcodes obs/action layout for the expert. Envs that support imitation return an ImitationAdapter from imitation_adapter(); PPO calls it on each minibatch to get expert obs, sample mask, and action indices. --imitate without an adapter raises clearly.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
PPO no longer hardcodes obs/action layout for the expert. Envs that support imitation return an ImitationProjector from
imitation_projector(); PPO calls it on each minibatch to get expert obs, sample mask, and action indices. --imitate without an adapter raises clearly.